Related Experiment Video
Updated: Aug 8, 2025

Author Spotlight: Exploring Breathing Techniques and Digital Solutions for Enhancing Running Performance
Published on: September 27, 2024
Constant Force-Tracking Control Based on Deep Reinforcement Learning in Dynamic Auscultation Environment
Tieyi Zhang1,2, Chao Chen1,2, Minglei Shu1,2
1School of Mathematics and Statistics, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, China.
This study introduces a deep reinforcement learning approach for intelligent medical robots performing dynamic auscultation. The novel control strategy ensures safe and accurate constant force tracking during simulated and real-world medical examinations.
Area of Science:
- Robotics
- Artificial Intelligence
- Medical Technology
Background:
- Intelligent medical robots can assist healthcare professionals with diagnoses and treatments, addressing personnel shortages.
- Dynamic medical auscultation presents challenges for robotic control due to the breathing process.
Purpose of the Study:
- To investigate the application of deep reinforcement learning for dynamic medical auscultation tasks.
- To develop a robust control strategy for intelligent medical robots in auscultation.
Main Methods:
- A constant force-tracking control method for dynamic environments was proposed.
- A physically characteristic modeling method was used to simulate dynamic breathing.
- An optimal reward function was designed for efficient control strategy learning.
Main Results:
- Simulation experiments showed tracking error within ±0.5 N for normal force.
- Real-world tests demonstrated effective constant force-tracking in medical auscultation.
- Contact force remained within a safe and stable range, averaging approximately 5.2 N.
Conclusions:
- The developed deep reinforcement learning control strategy is effective for dynamic medical auscultation.
- The approach ensures safe and stable robotic interaction during auscultation procedures.
Related Concept Videos
Neural Control of Respiration
Respiratory Centers in the Brainstem
Two primary areas comprise the respiratory center: the medullary respiratory center in the medulla oblongata and the pontine respiratory group in the pons. The...
Feedback control systems
Linear feedback systems are theoretical models that simplify analysis and design. These systems operate under the principle that their output is directly proportional to their input within certain ranges. For instance, an amplifier in a control system behaves linearly as long as the input signal remains within a specific range. However, most physical systems exhibit inherent nonlinearity...
Observational Learning
Physiological Control of Respiration
Breathing, a seemingly passive process, is regulated by the respiratory center in the brainstem. This center coordinates the involuntary control of respirations, which means it occurs without conscious effort, ensuring a smooth and uninterrupted pattern.
Regulation of Ventilation
The body maintains ventilation by monitoring levels of carbon dioxide (CO2), oxygen (O2), and hydrogen ion concentration (pH) in the arterial blood. Among these factors, the level of CO2 plays a crucial...
Open and closed-loop control systems
An open-loop control system operates without feedback from the output. It consists of two primary elements: the controller and the controlled process. The controller receives an input signal...
Reinforcement
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:

